Fast and privacy preserving distributed low-rank regression
Lists
Only you see this
Abstract
This paper proposes a fast and privacy preserving distributed algorithm for handling low-rank regression problems with nuclear norm constraint. Traditional projected gradient algorithms have high computation costs due to their projection steps when they are used to solve these problems. Our gossip-based algorithm, called the fast DeFW algorithm, overcomes this issue since it is projection-free. In particular, the algorithm incorporates a carefully designed decentralized power method step to reduce the complexity by distributed computation over network. Meanwhile, privacy is preserved as the agents do not exchange the private data, but only a random projection of them. We show that the fast DeFW algorithm converges for both convex and non-convex losses. As an application example, we consider the low-rank matrix completion problem and provide numerical results to support our findings.
BibTeX
@inproceedings{wai2017fast,
author = {Hoi-To Wai and Anna Scaglione and Jean Lafond and Eric Moulines},
title = {{Fast and privacy preserving distributed low-rank regression}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2017},
doi = {10.1109/icassp.2017.7952998},
}Loading related content...